AgentWorkforce · khaliqgant · May 13, 2026 · May 13, 2026 · May 13, 2026
diff --git a/docs/plans/deploy-v1.md b/docs/plans/deploy-v1.md
@@ -38,7 +38,7 @@ One file. One command. One contract.
 
 ### In
 
-- Persona JSON schema extension: `cloud`, `useSubscription`, `integrations`, `schedules`, `sandbox`, `memory`, `traits`, `onEvent`.
+- Persona JSON schema extension: `cloud`, `useSubscription`, `integrations`, `schedules`, `memory`, `onEvent`.
 - New package `@agentworkforce/runtime` — thin facade exposing `handler(...)` that wraps `agent({...})` from `@agent-relay/agent` (cloud proactive-runtime M1 SDK).
 - New package `@agentworkforce/deploy` — the deploy CLI logic; the existing `cli.ts` gets a `deploy` case that dispatches to it.
 - Daytona sandbox launcher used in the `--sandbox` run mode.
@@ -64,20 +64,29 @@ One file. One command. One contract.
 
 ## 3. Persona JSON schema diff
 
-All new fields are optional. A persona that does not set any of them continues to behave exactly as today — `workforce agent <id>` works unchanged. Set `cloud: true` and at least one trigger to opt into the new deploy surface.
+All new fields are optional. A persona that does not set any of them continues to behave exactly as today — `workforce agent <id>` works unchanged. Set `cloud: true` and at least one listener to opt into the new deploy surface.
+
+A persona listens for events. Three listener kinds exist in v1:
+
+- **clock** — cron `schedules[]` (§3.3).
+- **radio** — RelayFile integration event triggers, declared via `integrations.<provider>.triggers[]` (§3.2).
+- **inbox** — RelayCast targeted messages. Not yet modeled in v1; reserved.
+
+Two fields explored in earlier drafts were dropped before v1 ships:
+
+- **`traits`** was removed in v1. Personality is handled by the persona-personality-builder tool, which is out of scope for v1. Parsers reject any persona that still declares `traits` so old specs surface loudly during migration.
+- **`sandbox`** was removed in v1. Sandbox is on by default at deploy time; opt out with `workforce deploy --no-sandbox` or runtime config rather than per-persona JSON. Parsers reject any persona that still declares `sandbox` for the same reason.
 
 ### 3.1 Top-level additions
 
 | Field | Type | Required when | Meaning |
 |---|---|---|---|
 | `cloud` | `boolean` | always (default `false`) | When `true`, this persona is deployable. `workforce deploy` only operates on personas where this is `true`. |
 | `useSubscription` | `boolean` | optional | When `true`, inference uses the user's connected LLM subscription via `@agent-relay/cloud`'s provider link (no workforce-billed tokens). Triggers a `connectProvider` step at deploy time. |
-| `integrations` | `Record<string, IntegrationConfig>` | when persona has event triggers | Declares which Relayfile providers this agent needs and what events fire its handler. See §3.2. |
-| `schedules` | `Schedule[]` | when persona runs on cron | One or more cron triggers, registered with the runtime's `ctx.schedule.every(...)`. Each schedule has a `name` echoed back to the handler. See §3.3. |
-| `sandbox` | `boolean \| SandboxConfig` | optional | `true` (default) means agent runs inside a Daytona sandbox. `false` means the runner process owns its own filesystem. Object form lets you tune env / timeout. See §3.4. |
+| `integrations` | `Record<string, IntegrationConfig>` | when persona has event triggers | Declares which Relayfile providers this agent needs and what events fire its handler. The "radio" listener surface. See §3.2. |
+| `schedules` | `Schedule[]` | when persona runs on cron | One or more cron triggers, registered with the runtime's `ctx.schedule.every(...)`. Each schedule has a `name` echoed back to the handler. The "clock" listener surface. See §3.3. |
 | `memory` | `boolean \| MemoryConfig` | optional | Enables the agent-assistant memory subsystem. Scopes and TTL configurable. See §3.5. |
-| `traits` | `Traits` | optional, **only meaningful for interactive agents** | Mirrors `@agent-assistant/traits`: voice, formality, proactivity, etc. Applied when the agent posts to a chat surface (Slack, Relaycast). Headless agents (paraglide-style "Linear issue → ship") may omit this. See §3.6. |
-| `onEvent` | `string` | when `cloud: true` and any trigger declared | Path to a TS file (relative to the persona JSON) whose default export is the event handler. Sub-file references like `./agent.ts` and `./handlers/index.ts` are supported. See §4. |
+| `onEvent` | `string` | when `cloud: true` and any listener declared | Path to a TS file (relative to the persona JSON) whose default export is the event handler. Sub-file references like `./agent.ts` and `./handlers/index.ts` are supported. See §4. |
 
 ### 3.2 `integrations` shape
 
@@ -119,18 +128,16 @@ The act of stacking integrations is just declaring multiple keys. The act of lin
 - `cron` is a standard 5-field expression. `tz` defaults to `UTC`.
 - Multiple schedules are allowed. The runtime registers each with `ctx.schedule.every(cron, { tz, payload: { name } })`.
 
-### 3.4 `sandbox` shape
+### 3.4 Sandbox (deploy-time, not persona-level)
 
-```jsonc
-"sandbox": true                                          // default
-"sandbox": { "enabled": true, "timeoutSeconds": 1800, "env": { "FOO": "bar" } }
-"sandbox": false                                         // run in the runner process's fs
-```
+Sandbox configuration was lifted out of the persona spec in v1. The deploy
+CLI runs every cloud persona inside a Daytona sandbox by default; pass
+`workforce deploy --no-sandbox` (or set runtime config) to opt out. The
+sandbox image, timeout, and env are decided at deploy time:
 
-- Image is **not** user-configurable in v1. Workforce picks a standard image (`node-22` baseline) for the default Daytona sandbox. We can add `image` later if a real demand surfaces; eliminating the field keeps the v1 contract small.
-- `timeoutSeconds` caps a single handler invocation. Default 1800s.
-- `env` adds env vars on top of the auto-injected secrets (Relayfile connection tokens, harness inference creds, etc.).
-- When `sandbox: false`, the agent's `ctx.sandbox` still exists but points at the runner's own process — useful for `--dev` iteration, **not** what we recommend for production.
+- Image is **not** user-configurable in v1. Workforce picks a standard image (`node-22` baseline) for the default Daytona sandbox.
+- The sandbox-client default exec timeout (~600s, see `packages/deploy/src/modes/sandbox-client.ts`) applies to every run. Per-persona handler timeouts continue to live on `harnessSettings.timeoutSeconds`.
+- Auto-injected secrets (Relayfile connection tokens, harness inference creds) come from the deploy environment, not the persona JSON.
 
 ### 3.5 `memory` shape
 
@@ -148,25 +155,17 @@ The act of stacking integrations is just declaring multiple keys. The act of lin
 - Implementation: the runtime wires `@agent-assistant/memory` with the supermemory adapter (matching sage today). API key is pulled from workforce-managed env, not declared in the persona.
 - `scopes` is the only field with real semantic weight: session-only memory is wiped per handler; user-scope persists across the user's invocations of this agent; workspace persists across all users.
 - `autoPromote` flips on the sage turn-recorder pattern — agent decides if session content is worth promoting.
-- **No `memoryMd` file.** Memory is config, not prose. Personality goes in `traits` and `description`.
+- **No `memoryMd` file.** Memory is config, not prose. Personality goes in `description` (and, in a future iteration, in the persona-personality-builder tool's output).
 
-### 3.6 `traits` shape
-
-Direct mapping to `@agent-assistant/traits`:
-
-```jsonc
-"traits": {
-  "voice": "professional-warm",
-  "formality": "low",
-  "proactivity": "medium",
-  "riskPosture": "conservative",
-  "domain": "engineering",
-  "vocabulary": ["PR", "diff", "CI"],
-  "preferMarkdown": true
-}
-```
+### 3.6 Traits (removed in v1)
 
-Only used when the runtime renders into a conversational surface (Slack message, Relaycast post, GitHub PR comment). Skip the field entirely for headless agents — saves the runtime a subsystem registration.
+`traits` was explored in earlier drafts as a direct mapping to
+`@agent-assistant/traits` (voice, formality, proactivity, risk posture,
+domain vocabulary, markdown preference). It is **removed from the v1
+persona spec**: personality is handled by the persona-personality-builder
+tool, which is out of scope for v1. Parsers reject any persona that
+still declares `traits` so old specs surface during migration. The
+replacement story will be designed alongside that tool's first iteration.
 
 ### 3.7 Trigger-name registry
 
@@ -242,7 +241,7 @@ interface WorkforceCtx {
     cancel(name: string): Promise<void>;
   };
 
-  // Persona metadata (id, traits, harness tier defaults, etc.) — read-only
+  // Persona metadata (id, listener config, harness tier defaults, etc.) — read-only
   persona: PersonaSpec;
 }
 
@@ -254,7 +253,7 @@ export function handler<I extends IntegrationKeys>(
 Implementation notes:
 - `handler(...)` reads the persona JSON adjacent to the entrypoint (workforce bundles them together). At cold-start it:
   1. Calls `agent({ workspace, schedule, watch, inbox, onEvent: shim })` from `@agent-relay/agent`, mapping `persona.integrations` to `watch` and `persona.schedules` to `schedule`.
-  2. Builds `ctx` once per agent boot: opens Daytona handle (if `sandbox: true`), wires Relayfile-derived clients, attaches memory adapter.
+  2. Builds `ctx` once per agent boot: opens Daytona handle (sandbox is on by default at deploy time; opt out with `workforce deploy --no-sandbox`), wires Relayfile-derived clients, attaches memory adapter.
   3. The `shim` reshapes the raw envelope from `@agent-relay/agent` into the `WorkforceEvent` discriminated union and invokes the user's `fn(ctx, event)`.
 - The user never imports `@agent-relay/agent` directly. Workforce owns the ergonomics. If the underlying SDK churns, we absorb the diff here.
 - The SDK doors stay open for power users: we re-export `agent` from `@agentworkforce/runtime/raw` so anyone who wants the lower-level surface can drop down. This matters for nightcto-shaped projects that outgrow the persona contract.
@@ -354,7 +353,6 @@ Direct port of the proactive-agents weekly-digest pattern.
   "cloud": true,
   "integrations": { "github": { "scope": { "repo": "AgentWorkforce/weekly-digest" } } },
   "schedules": [{ "name": "weekly", "cron": "0 9 * * 6", "tz": "UTC" }],
-  "sandbox": true,
   "memory": { "enabled": true, "scopes": ["workspace"], "ttlDays": 90 },
   "onEvent": "./agent.ts",
   "tiers": { ... standard codex/opencode tiers ... }
@@ -385,9 +383,7 @@ Direct port of the proactive-agents weekly-digest pattern.
     },
     "slack": { "triggers": [{ "on": "app_mention" }] }
   },
-  "sandbox": true,
   "memory": { "enabled": true, "scopes": ["session", "workspace"] },
-  "traits": { "voice": "professional-warm", "formality": "low", "preferMarkdown": true },
   "onEvent": "./agent.ts",
   "tiers": { ... }
 }
@@ -409,7 +405,7 @@ workforce/
 │   ├── cli/                          # add `deploy`, `login` cases
 │   ├── persona-kit/                  # extend PersonaSpec schema (§3)
 │   │   └── src/
-│   │       ├── types.ts              # +CloudFields, +IntegrationConfig, +Schedule, +Sandbox, +Memory, +Traits
+│   │       ├── types.ts              # +CloudFields, +IntegrationConfig, +Schedule, +Memory
 │   │       ├── parse.ts              # extend parsePersonaSpec to read new fields
 │   │       └── triggers.ts           # NEW — known triggers registry (§3.7)
 │   ├── harness-kit/                  # no changes for v1
@@ -494,7 +490,7 @@ If a track slips, §10's fallback applies: ship `--dev` end-to-end with `weekly-
 Tasks that are mechanical, well-specified, and don't gate on my decisions — perfect for a codex agent spawned via `workforce agent code-implementer` or a similar persona:
 
 1. **Trigger registry expansion** — fill out `packages/persona-kit/src/triggers.ts` with the full set of known trigger names per Tier-1 provider (Linear, GitHub, Slack, Notion, Jira) by reading the Relayfile provider docs in `/Users/khaliqgant/Projects/AgentWorkforce/relayfile/docs/`.
-2. **Test fixtures** — generate sample `persona.json` files exercising every optional combination (with/without traits, sandbox false, multi-schedule, etc.) into `packages/persona-kit/src/__fixtures__/`.
+2. **Test fixtures** — generate sample `persona.json` files exercising every optional combination (multi-schedule, with/without memory, multi-provider integrations, etc.) into `packages/persona-kit/src/__fixtures__/`.
 3. **JSON Schema export** — emit a JSON Schema from the extended `PersonaSpec` for editor autocomplete. New script: `packages/persona-kit/scripts/emit-schema.mjs`. Wire to `pnpm run build` so it ships with the package.
 4. **Example expansion** — write a third example, `examples/linear-shipper/` (the paraglide pattern: Linear issue created → drive to PR), purely against the runtime substrate I land in §9.1.
 5. **README polish** — once the deploy command is real, codex agent rewrites the workforce README to lead with the deploy story.

diff --git a/examples/weekly-digest/persona.json b/examples/weekly-digest/persona.json
@@ -35,7 +35,6 @@
       "tz": "UTC"
     }
   ],
-  "sandbox": true,
   "memory": {
     "enabled": true,
     "scopes": [

diff --git a/packages/deploy/src/modes/sandbox.ts b/packages/deploy/src/modes/sandbox.ts
@@ -59,7 +59,12 @@ export const sandboxLauncher: ModeLauncher = {
       throw err;
     }
 
-    const sandboxTimeoutSeconds = resolveTimeoutSeconds(input.persona.sandbox);
+    // Per-persona sandbox tuning (`persona.sandbox.timeoutSeconds`) was
+    // removed in deploy-v1; the sandbox-client default (600s, see
+    // sandbox-client.ts) applies to every run. Persona-level harness
+    // timeouts (`harnessSettings.timeoutSeconds`) are honored by the
+    // harness inside the sandbox, not by the sandbox `exec` envelope.
+    const sandboxTimeoutSeconds: number | undefined = undefined;
 
     let stopping = false;
     const stop = async (): Promise<void> => {
@@ -149,14 +154,6 @@ export function resolveSandboxClient(
   });
 }
 
-function resolveTimeoutSeconds(sandbox: ModeLaunchInput['persona']['sandbox']): number | undefined {
-  if (sandbox === undefined || sandbox === true || sandbox === false) return undefined;
-  if (typeof sandbox.timeoutSeconds === 'number' && sandbox.timeoutSeconds > 0) {
-    return sandbox.timeoutSeconds;
-  }
-  return undefined;
-}
-
 // Re-exported for tests + power users wanting to compose the client manually.
 export {
   SANDBOX_BUNDLE_DIR,

diff --git a/packages/persona-kit/src/index.ts b/packages/persona-kit/src/index.ts
@@ -32,14 +32,11 @@ export type {
   PersonaMemoryScope,
   PersonaMount,
   PersonaPermissions,
-  PersonaSandbox,
-  PersonaSandboxConfig,
   PersonaSchedule,
   PersonaSelection,
   PersonaSkill,
   PersonaSpec,
   PersonaTag,
-  PersonaTraits,
   SidecarMdMode,
   SkillInstall,
   SkillMaterializationOptions,
@@ -69,13 +66,11 @@ export {
   parseOnEvent,
   parsePermissions,
   parsePersonaSpec,
-  parseSandbox,
   parseSchedules,
   parseSkills,
   parseStringList,
   parseStringMap,
   parseTags,
-  parseTraits,
   resolveSidecar,
   sidecarSelectionFields
 } from './parse.js';